Online education intelligent monitoring system

Abstract

The invention relates to an online education intelligent monitoring system, which comprises an intelligent judgment device and a monitoring device, the identification module is used for intelligently identifying the probability that the learning attitude-losing pattern exists in the tail end analysis picture by adopting a deep neural network model according to the gray value of each pixel point in the tail end analysis picture, the pixel point gradient of each foreground pixel point, the coordinate value of each edge pixel point and the binary value of the learning attitude-losing pattern; and the information transmission equipment is used for marking the student client as a key monitoring client when the received probability is greater than or equal to a set probability threshold. The online education intelligent monitoring system is simple and convenient to operate and wide in application. The deep neural network model can be adopted to intelligently identify whether the student is in the learning posture losing state based on various visual information, so that reliable reference data is provided for automatic and intelligent monitoring of online education.

Description

Technical Field

[0001] The present invention relates to the field of online education, and in particular to an online education intelligent monitoring system. Background Art

[0002] With the advent of the knowledge economy, people's learning patterns have been impacted unprecedentedly, and various new learning patterns have emerged like a tide. Among all learning patterns, the most impactful one is the network learning that has emerged with the development of network technology, also known as online education. It is a new way of online learning by establishing an education platform on the Internet and allowing students to use the Internet to learn online. This online learning method is a new learning environment composed of multimedia network learning resources, online learning communities and network technology platforms. Compared with other learning patterns, it has incomparable advantages.

[0003] However, in the course of online education, since teachers are at the remote end of the teaching, they cannot effectively observe the learning status of each student, for example, whether the students are in a state of distorted learning posture. At the same time, the teacher's deterrent power on students is greatly reduced, which makes it easy for students to fall into a state of distorted learning posture and cannot extricate themselves, or get used to using distorted learning posture to study without correcting it, which seriously affects the teaching quality of online education. Summary of the invention

[0004] In order to solve the technical problems in the related fields, the present invention provides an online education intelligent monitoring system, which can parse the grayscale values ​​corresponding to each pixel point in the terminal analysis picture, the coordinate values ​​corresponding to each edge pixel point, and the pixel gradients corresponding to each foreground pixel point in the terminal analysis picture, and extract the binary value of the learning posture loss pattern, wherein the learning posture loss pattern is a pattern corresponding to a learning posture that deviates from the standard learning posture, and adopts a deep neural network model to intelligently identify the probability of the learning posture loss pattern existing in the terminal analysis picture according to the grayscale values ​​corresponding to each pixel point in the terminal analysis picture, the coordinate values ​​corresponding to each edge pixel point, the pixel gradients corresponding to each foreground pixel point in the terminal analysis picture, and the binary value of the learning posture loss pattern, thereby providing reliable reference data for the automated and intelligent monitoring of online education, wherein the deep neural network model used to perform the intelligent identification of the probability of the learning posture loss pattern is a deep neural network after multiple learning operations, and the number of learning operations is monotonically positively correlated with the number of pixels in the online monitoring picture, thereby designing artificial intelligence models with different structures for different monitoring systems.

[0005] According to the present invention, there is provided an online education intelligent monitoring system, the system comprising: An online monitoring mechanism is used to provide the online education operator with monitoring images of the student learning scene at the student client to be output as online monitoring images; A front-end analysis mechanism, connected to the online monitoring mechanism, for performing point image restoration processing on the received online monitoring picture to obtain and output a corresponding front-end analysis picture; A secondary-end parsing mechanism, connected to the front-end parsing mechanism, for performing frequency domain enhancement processing on the received front-end parsed picture to obtain and output a corresponding secondary-end parsed picture; The terminal parsing mechanism is connected to the secondary parsing structure and is used to perform nonlinear grayscale transformation processing on the received secondary parsing picture to obtain and output the corresponding terminal parsing picture; An intelligent judgment device is connected to the terminal parsing mechanism, and is used to parse the grayscale values ​​corresponding to the pixels in the terminal parsing picture, the coordinate values ​​corresponding to the edge pixels, and the pixel gradients corresponding to the foreground pixels in the terminal parsing picture, and extract the binary value of the learning posture loss pattern, and use a deep neural network model to intelligently identify the probability that the learning posture loss pattern exists in the terminal parsing picture according to the grayscale values ​​corresponding to the pixels in the terminal parsing picture, the coordinate values ​​corresponding to the edge pixels, the pixel gradients corresponding to the foreground pixels in the terminal parsing picture, and the binary value of the learning posture loss pattern; Among them, parsing each grayscale value corresponding to each pixel point in the terminal parsing picture, each coordinate value corresponding to each edge pixel point, and each pixel gradient corresponding to each foreground pixel point in the terminal parsing picture, and extracting the binary value of the learning posture loss pattern at the same time includes: the learning posture loss pattern is a pattern corresponding to a learning posture that deviates from a standard learning posture; Among them, a deep neural network model is used to intelligently identify the probability that the learning posture loss pattern exists in the terminal analysis picture according to each grayscale value corresponding to each pixel point in the terminal analysis picture, each coordinate value corresponding to each edge pixel point, each pixel gradient corresponding to each foreground pixel point in the terminal analysis picture, and the binary value of the learning posture loss pattern, including: the deep neural network model is a deep neural network after multiple learning operations and the number of learning operations is monotonically positively correlated with the number of pixels in the online monitoring picture.

[0006] It can be seen that the present invention has at least the following three significant substantive features: Substantive feature 1: Analyze the grayscale values ​​corresponding to each pixel in the terminal analysis picture, the coordinate values ​​corresponding to each edge pixel, and the pixel gradients corresponding to each foreground pixel in the terminal analysis picture, and extract the binary value of the learning posture loss pattern at the same time, where the learning posture loss pattern is a pattern corresponding to the learning posture that deviates from the standard learning posture; Substantive feature 2: A deep neural network model is used to intelligently identify the probability of the learning posture loss pattern existing in the terminal analysis picture according to the grayscale values ​​corresponding to each pixel point in the terminal analysis picture, the coordinate values ​​corresponding to each edge pixel point, the pixel gradients corresponding to each foreground pixel point in the terminal analysis picture, and the binary value of the learning posture loss pattern, thereby providing reliable reference data for the automated and intelligent monitoring of online education; Substantive feature three: The deep neural network model used to perform intelligent identification of the probability of existence of learning posture loss patterns is a deep neural network after multiple learning operations, and the number of learning operations is monotonically positively correlated with the number of pixels in the online monitoring screen, thereby designing artificial intelligence models with different structures for different monitoring systems.

[0007] The online education intelligent monitoring system of the present invention is easy to operate and widely used. Since a deep neural network model can be used to intelligently identify whether a student is in a learning error state based on various visual information, reliable reference data can be provided for the automated and intelligent monitoring of online education. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein: Figure 1 It is a diagram showing the internal structure of an online education intelligent monitoring system according to the first embodiment of the present invention.

[0009] Figure 2 It is a diagram showing the internal structure of an online education intelligent monitoring system according to a second embodiment of the present invention.

[0010] Figure 3 1 is an internal structure diagram of an online education intelligent monitoring system according to a third embodiment of the present invention. DETAILED DESCRIPTION

[0011] The implementation scheme of the online education intelligent monitoring system of the present invention will be described in detail below with reference to the accompanying drawings.

[0012] Figure 1 The internal structure diagram of the online education intelligent monitoring system according to the first embodiment of the present invention is shown, and the system includes: An online monitoring mechanism is used to provide the online education operator with monitoring images of the student learning scene at the student client to be output as online monitoring images; Specifically, the online monitoring mechanism is used to provide the online education operator with a monitoring screen of the student learning scene at the student client as an online monitoring screen output, including: the online monitoring mechanism has a built-in photoelectric sensing unit, which is used to perform a photoelectric sensing operation on the monitoring scene of the student learning scene at the student client; A front-end analysis mechanism, connected to the online monitoring mechanism, for performing point image restoration processing on the received online monitoring picture to obtain and output a corresponding front-end analysis picture; A secondary-end parsing mechanism, connected to the front-end parsing mechanism, for performing frequency domain enhancement processing on the received front-end parsed picture to obtain and output a corresponding secondary-end parsed picture; The terminal parsing mechanism is connected to the secondary parsing structure and is used to perform nonlinear grayscale transformation processing on the received secondary parsing picture to obtain and output the corresponding terminal parsing picture; An intelligent judgment device is connected to the terminal parsing mechanism, and is used to parse the grayscale values ​​corresponding to the pixels in the terminal parsing picture, the coordinate values ​​corresponding to the edge pixels, and the pixel gradients corresponding to the foreground pixels in the terminal parsing picture, and extract the binary value of the learning posture loss pattern, and use a deep neural network model to intelligently identify the probability that the learning posture loss pattern exists in the terminal parsing picture according to the grayscale values ​​corresponding to the pixels in the terminal parsing picture, the coordinate values ​​corresponding to the edge pixels, the pixel gradients corresponding to the foreground pixels in the terminal parsing picture, and the binary value of the learning posture loss pattern; Specifically, the MATLAB toolbox can be selected to implement the test and simulation of the data processing process of using a deep neural network model to intelligently identify the probability that the learning posture loss pattern exists in the terminal analysis picture according to the grayscale values ​​corresponding to each pixel point in the terminal analysis picture, the coordinate values ​​corresponding to each edge pixel point, and the pixel gradients corresponding to each foreground pixel point in the terminal analysis picture and the binary values ​​of the learning posture loss pattern; An information transmission device connected to the intelligent judgment device, used to mark the student client as a key monitoring client when the received probability is greater than or equal to a set probability threshold, otherwise, the student client is unmarked as a key monitoring client; Among them, parsing each grayscale value corresponding to each pixel point in the terminal parsing picture, each coordinate value corresponding to each edge pixel point, and each pixel gradient corresponding to each foreground pixel point in the terminal parsing picture, and extracting the binary value of the learning posture loss pattern at the same time includes: the learning posture loss pattern is a pattern corresponding to a learning posture that deviates from a standard learning posture; Among them, the deep neural network model is used to intelligently identify the probability that the learning posture loss pattern exists in the terminal analysis picture according to each gray value corresponding to each pixel point in the terminal analysis picture, each coordinate value corresponding to each edge pixel point, and each pixel gradient corresponding to each foreground pixel point in the terminal analysis picture and the binary value of the learning posture loss pattern, including: the deep neural network model is a deep neural network after multiple learning operations, and the number of learning operations is monotonically positively correlated with the number of pixels in the online monitoring picture; The deep neural network model is a deep neural network after multiple learning operations and the number of learning operations is monotonically positively correlated with the number of pixels of the online monitoring screen, including: using a numerical mapping function to represent a numerical mapping relationship of monotonically positively correlated number of learning operations with the number of pixels of the online monitoring screen; Among them, using a deep neural network model to intelligently identify the probability that the learning posture loss pattern exists in the terminal parsing picture according to each grayscale value corresponding to each pixel point in the terminal parsing picture, each coordinate value corresponding to each edge pixel point, each pixel gradient corresponding to each foreground pixel point in the terminal parsing picture, and the binary value of the learning posture loss pattern also includes: synchronously inputting each grayscale value corresponding to each pixel point in the terminal parsing picture, each coordinate value corresponding to each edge pixel point, each pixel gradient corresponding to each foreground pixel point in the terminal parsing picture, and the binary value of the learning posture loss pattern into the deep neural network model, and executing the deep neural network model to obtain the probability that the learning posture loss pattern output by the deep neural network model exists in the terminal parsing picture.

[0013] Figure 2 It is a diagram showing the internal structure of an online education intelligent monitoring system according to a second embodiment of the present invention.

[0014] exist Figure 2 In, with Figure 1 Differently, the online education intelligent monitoring system shown in the second embodiment of the present invention may also include: A parallel data interface, for connecting the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device, respectively, to receive data from the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device, respectively, and to send parallel data from a parallel data bus to the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device, respectively; Among them, the parallel data interface is used for connecting the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device respectively, so as to receive data from the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device respectively, and send parallel data from the parallel data bus to the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device respectively, including: the parallel data bus is one of a 16-bit parallel data bus and a 32-bit parallel data bus.

[0015] Figure 3 1 is an internal structure diagram of an online education intelligent monitoring system according to a third embodiment of the present invention.

[0016] exist Figure 3 In, with Figure 1 Differently, the online education intelligent monitoring system shown in the third embodiment of the present invention may also include: The user control interface is respectively connected to the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device, and is used to receive user control instructions for the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device.

[0017] Next, the specific structure of the online education intelligent monitoring system of the present invention will be further described.

[0018] In the online education intelligent monitoring system according to any embodiment of the present invention: The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are connected to the same quartz oscillation device to obtain the timing data provided by the quartz oscillation device, and the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the same content storage chip, and the content storage chip is one of FLASH flash memory, SDRAM memory chip and DDR memory chip.

[0019] In the online education intelligent monitoring system according to any embodiment of the present invention: The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the same IIC control bus, and are used to receive various control commands sent by the IIC control bus, and the various control commands are used to respectively configure various working parameters of the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device; The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the IIC control bus and are used to receive various control instructions sent through the IIC control bus.

[0020] In the online education intelligent monitoring system according to any embodiment of the present invention: The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the same MCU controller, and are used for switching the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device between the sleep mode and the working mode under the control of the same MCU controller; And wherein, the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the same MCU controller, and are used for switching the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device between the sleep mode and the working mode respectively under the control of the same MCU controller, including: the same MCU controller is designed based on the ARM13 core.

[0021] In addition, in the online education intelligent monitoring system, a numerical mapping function is used to represent the monotonically positive correlation between the number of learning operations and the number of pixel points of the online monitoring screen, including: in the numerical mapping function, the number of pixel points of the online monitoring screen is used as the input content of the numerical mapping function, and the number of learning operations is used as the output content of the numerical mapping function.

[0022] The above embodiments are merely examples for implementing the present invention, and the present invention is not limited thereto. Various modifications to these embodiments are within the scope of the present invention. It can be understood from the above contents that various other embodiments are possible within the scope of the present invention.

Claims

1. An online education intelligent monitoring system, characterized in that: The system comprises: An online monitoring mechanism is used to provide the online education operator with monitoring images of the student learning scene at the student client to be output as online monitoring images; A front-end analysis mechanism, connected to the online monitoring mechanism, for performing point image restoration processing on the received online monitoring picture to obtain and output a corresponding front-end analysis picture; A secondary-end parsing mechanism, connected to the front-end parsing mechanism, for performing frequency domain enhancement processing on the received front-end parsed picture to obtain and output a corresponding secondary-end parsed picture; The terminal parsing mechanism is connected to the secondary parsing structure and is used to perform nonlinear grayscale transformation processing on the received secondary parsing picture to obtain and output the corresponding terminal parsing picture; An intelligent judgment device is connected to the terminal parsing mechanism, and is used to parse the grayscale values ​​corresponding to the pixels in the terminal parsing picture, the coordinate values ​​corresponding to the edge pixels, and the pixel gradients corresponding to the foreground pixels in the terminal parsing picture, and extract the binary value of the learning posture loss pattern, and use a deep neural network model to intelligently identify the probability that the learning posture loss pattern exists in the terminal parsing picture according to the grayscale values ​​corresponding to the pixels in the terminal parsing picture, the coordinate values ​​corresponding to the edge pixels, the pixel gradients corresponding to the foreground pixels in the terminal parsing picture, and the binary value of the learning posture loss pattern; An information transmission device connected to the intelligent judgment device, used to mark the student client as a key monitoring client when the received probability is greater than or equal to a set probability threshold, otherwise, the student client is unmarked as a key monitoring client; Among them, parsing each grayscale value corresponding to each pixel point in the terminal parsing picture, each coordinate value corresponding to each edge pixel point, and each pixel gradient corresponding to each foreground pixel point in the terminal parsing picture, and extracting the binary value of the learning posture loss pattern at the same time includes: the learning posture loss pattern is a pattern corresponding to a learning posture that deviates from a standard learning posture; Among them, a deep neural network model is used to intelligently identify the probability that the learning posture loss pattern exists in the terminal analysis picture according to each grayscale value corresponding to each pixel point in the terminal analysis picture, each coordinate value corresponding to each edge pixel point, each pixel gradient corresponding to each foreground pixel point in the terminal analysis picture, and the binary value of the learning posture loss pattern, including: the deep neural network model is a deep neural network after multiple learning operations and the number of learning operations is monotonically positively correlated with the number of pixels in the online monitoring picture.

2. The online education intelligent monitoring system according to claim 1, characterized in that: The deep neural network model is a deep neural network after multiple learning operations and the number of learning operations is monotonically positively correlated with the number of pixels of the online monitoring screen, including: using a numerical mapping function to represent a numerical mapping relationship of monotonically positively correlated number of learning operations with the number of pixels of the online monitoring screen; Among them, using a deep neural network model to intelligently identify the probability that the learning posture loss pattern exists in the terminal parsing picture according to each grayscale value corresponding to each pixel point in the terminal parsing picture, each coordinate value corresponding to each edge pixel point, each pixel gradient corresponding to each foreground pixel point in the terminal parsing picture, and the binary value of the learning posture loss pattern also includes: synchronously inputting each grayscale value corresponding to each pixel point in the terminal parsing picture, each coordinate value corresponding to each edge pixel point, each pixel gradient corresponding to each foreground pixel point in the terminal parsing picture, and the binary value of the learning posture loss pattern into the deep neural network model, and executing the deep neural network model to obtain the probability that the learning posture loss pattern output by the deep neural network model exists in the terminal parsing picture.

3. The online education intelligent monitoring system according to claim 2, characterized in that: The system further comprises: A parallel data interface, for connecting the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device, respectively, to receive data from the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device, respectively, and to send parallel data from a parallel data bus to the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device, respectively; Among them, the parallel data interface is used for connecting the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device respectively, so as to receive data from the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device respectively, and send parallel data from the parallel data bus to the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device respectively, including: the parallel data bus is one of a 16-bit parallel data bus and a 32-bit parallel data bus.

4. The online education intelligent monitoring system according to claim 3, characterized in that: The system further comprises: The user control interface is respectively connected to the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device, and is used to receive user control instructions for the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device.

5. The online education intelligent monitoring system according to any one of claims 2 to 4, characterized in that: The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are connected to the same quartz oscillation device to obtain the timing data provided by the quartz oscillation device, and the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the same content storage chip, and the content storage chip is one of FLASH flash memory, SDRAM memory chip and DDR memory chip.

6. The online education intelligent monitoring system according to any one of claims 2 to 4, characterized in that: The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the same IIC control bus, and are used to receive various control commands sent by the IIC control bus, and the various control commands are used to respectively configure various working parameters of the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device.

7. The online education intelligent monitoring system according to claim 6, characterized in that: The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the IIC control bus and are used to receive various control instructions sent through the IIC control bus.

8. The online education intelligent monitoring system according to any one of claims 2 to 4, characterized in that: The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the same MCU controller, and are used for switching the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device between the sleep mode and the working mode under the control of the same MCU controller.

9. The online education intelligent monitoring system according to claim 8, characterized in that: The front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device are respectively connected to the same MCU controller, and are used for switching the front-end parsing mechanism, the secondary-end parsing mechanism, the terminal parsing mechanism and the intelligent judgment device between the sleep mode and the working mode under the control of the same MCU controller, including: the same MCU controller is designed based on the ARM13 core.

Images